#tensorparallelism

Live, measured metrics for the hashtag #tensorparallelism from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.

hashtag.org network · sponsored

Own #tensorparallelism

This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.

$5.00/ year · 17-character #name
Claim #tensorparallelism — $5.00/yr→
Annual, renews each year
Buy on hashtag.space (web3)
one-timepay once, yours for life
card via hashtag.org · tokens via hashtag.space
0
Uses / 7 days
Mastodon
0
Accounts / 7 days
Mastodon
4
Recent posts
Mastodon
~0/hr
Recent pace
Mastodon · last 4
0
Avg reactions / post
Mastodon · last 4

Day-by-day usage

measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 10:04 UTC
0
07-21
0
07-22
0
07-23
0
07-24
0
07-25
0
07-26
0
07-27

0 uses by 0 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.

Related hashtags

measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-27 10:04 UTC

No related tags with measured usage found for #tensorparallelism.

Live pulse

measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 10:04 UTC

Everything below is measured over the latest 4 public posts (spanning ~2795 hours).

Posting hours (UTC)

00:0012:0023:00

Languages: English (4)

Avg boosts / post: 0

Top of the latest posts

  • Alex Cheema (@alexocheema) Kimi K3를 로컬에서 구동하기 위해 512GB M3 Ultra Mac Studio 4대(총 2TB 메모리)를 Thunderbolt 5 기반 RDMA로 연결하는 구성을 제안했다. MTP와 텐서 병렬화를 적용하면 루머상 모델 규모 기준 30 tok/s 이상을 기대하지만, 프리필 성능은 느릴 것으로 전망했다. https://x.com/alexocheema/status/2077906

    ainews@[email protected]♥ 0↻ 02026-07-17 10:54 UTCView post →

  • Alex Cheema (@alexocheema) Kimi K3를 데스크톱에서 구동하기 위해 512GB M3 Ultra Mac Studio 4대(총 2TB 메모리)를 쓰는 구성을 제안했다. Thunderbolt 5 기반 RDMA, 텐서 병렬화 및 MTP를 이용하면 루머상의 모델 규모 기준 30 tok/s 이상을 예상하지만, 프리필 성능은 느릴 것으로 전망했다. 활성 파라미터 수는 아직 확인되지 않은 추정치다. https://x.

    ainews@[email protected]♥ 0↻ 02026-07-17 07:54 UTCView post →

  • Alex Cheema (@alexocheema) MacBook 여러 대를 RDMA로 데이지 체인 연결해 최대 4대까지 1T 파라미터 모델을 선형 확장으로 실행할 수 있다는 내용입니다. 새로운 ‘LAN party’가 아닌 ‘RDMA party’라는 표현으로, 대형 모델 추론/병렬화에 MacBook과 RDMA를 활용하는 흥미로운 AI 인프라 사용 사례를 소개합니다. https://x.com/alexocheema/status/203

    ainews@[email protected]♥ 0↻ 02026-03-23 03:47 UTCView post →

Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/tensorparallelism